| { |
| "best_metric": 0.23382095992565155, |
| "best_model_checkpoint": "distilbert/distilbert-base-uncased-lora-text-classification\\checkpoint-2021", |
| "epoch": 0.9997526589166461, |
| "eval_steps": 500, |
| "global_step": 2021, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.24734108335394508, |
| "grad_norm": 0.8207709789276123, |
| "learning_rate": 7.525977238990599e-05, |
| "loss": 0.5518, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.49468216670789017, |
| "grad_norm": 1.7094056606292725, |
| "learning_rate": 5.0519544779811976e-05, |
| "loss": 0.355, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.7420232500618352, |
| "grad_norm": 1.3247127532958984, |
| "learning_rate": 2.5779317169717964e-05, |
| "loss": 0.3014, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.9893643334157803, |
| "grad_norm": 1.1423085927963257, |
| "learning_rate": 1.0390895596239487e-06, |
| "loss": 0.2843, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.9997526589166461, |
| "eval_accuracy": { |
| "accuracy": 0.8917183667580436 |
| }, |
| "eval_loss": 0.23382095992565155, |
| "eval_runtime": 57.5816, |
| "eval_samples_per_second": 240.737, |
| "eval_steps_per_second": 60.193, |
| "step": 2021 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2021, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4349609601073152.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
